© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 2821
    Prev
    Next
    INDEX
    Explanations

    sequences that indicate significant temporal events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCancelled
    -0.90
    SPATH
    -0.77
    CrossRef
    -0.67
     متحده
    -0.65
     Oates
    -0.64
     Damit
    -0.63
     TPA
    -0.63
    السكان
    -0.63
    ItemBackground
    -0.61
    DockStyle
    -0.61
    POSITIVE LOGITS
     five
    0.91
     four
    0.89
     six
    0.89
     three
    0.87
    six
    0.81
     fünf
    0.77
     seven
    0.76
    three
    0.75
    four
    0.73
    SIX
    0.72
    Activations Density 1.050%

    No Known Activations